Zero-Shot Clinical Questionnaire Filling From Human-Machine Interactions

Farnaz Ghassemi Toudeshki, Philippe Jolivet, Alexandre Durand-Salmon, Anna Liednikova


Abstract
In clinical studies, chatbots mimicking doctor-patient interactions are used for collecting information about the patient’s health state. Later, this information needs to be processed and structured for the doctor. One way to organize it is by automatically filling the questionnaires from the human-bot conversation. It would help the doctor to spot the possible issues. Since there is no such dataset available for this task and its collection is costly and sensitive, we explore the capacities of state-of-the-art zero-shot models for question answering, textual inference, and text classification. We provide a detailed analysis of the results and propose further directions for clinical questionnaire filling.
Anthology ID:
2021.mrqa-1.5
Volume:
Proceedings of the 3rd Workshop on Machine Reading for Question Answering
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Venues:
EMNLP | MRQA
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
51–62
Language:
URL:
https://aclanthology.org/2021.mrqa-1.5
DOI:
10.18653/v1/2021.mrqa-1.5
Bibkey:
Cite (ACL):
Farnaz Ghassemi Toudeshki, Philippe Jolivet, Alexandre Durand-Salmon, and Anna Liednikova. 2021. Zero-Shot Clinical Questionnaire Filling From Human-Machine Interactions. In Proceedings of the 3rd Workshop on Machine Reading for Question Answering, pages 51–62, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Zero-Shot Clinical Questionnaire Filling From Human-Machine Interactions (Ghassemi Toudeshki et al., MRQA 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/2021.mrqa-1.5.pdf
Data
RACE